Geekbench ML Score

2653
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date June 18 2022 08:27 AM
Views 1

System Information

System Information
Operating System Android 12
Model samsung SM-S901U
Model IDsamsung SM-S901U
Motherboard taro
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3400 revision 0
Base Frequency 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.50 GHz
Cluster 31 Core @ 3.00 GHz
Memory Information
Size 7.05 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1016
108.9 IPS
 
Image Classification (F16)
100% 7790
834.7 IPS
 
Image Classification (I8)
80% 16486
1.77 KIPS
 
Image Segmentation (F32)
100% 2364
14.6 IPS
 
Image Segmentation (F16)
100% 7037
43.5 IPS
 
Image Segmentation (I8)
89% 35004
216.2 IPS
 
Pose Estimation (F32)
100% 465
1.88 IPS
 
Pose Estimation (F16)
100% 9363
37.9 IPS
 
Pose Estimation (I8)
80% 52205
211.2 IPS
 
Object Detection (F32)
100% 868
30.4 IPS
 
Object Detection (F16)
100% 1415
49.7 IPS
 
Object Detection (I8)
53% 1710
60.0 IPS
 
Face Detection (F32)
100% 1470
16.9 IPS
 
Face Detection (F16)
97% 6940
79.7 IPS
 
Face Detection (I8)
76% 44982
516.8 IPS
 
Text Classification (F32)
100% 14
5.56 IPS
 
Text Classification (F16)
100% 578
228.7 IPS
 
Machine Translation (F32)
100% 910
140.2 IPS
 
Machine Translation (F16)
100% 918
141.4 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download